RMBench：面向记忆依赖型机器人操作的基准与策略设计洞察
RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
研究者提出 RMBench，一个包含 9 个操作任务的仿真基准，覆盖多个记忆复杂度层级，用于系统评估机器人操作策略的记忆能力。同时提出模块化策略 Mem-0，通过显式记忆组件支持受控消融实验，并在仿真与真实世界实验中揭示了现有策略的记忆局限及架构设计对记忆表现的影响。
Authors:Tianxing Chen, Yuran Wang, Mingleyang Li, Yan Qin, Hao Shi, Zixuan Li, Yifan Hu, Yingsheng Zhang, Kaixuan Wang, Yue Chen, Hongcheng Wang, Junjie Wang, Tianhang Yang, Renjing Xu, Ruihai Wu, Yao Mu, Yaodong Yang, Hao Dong, Ping Luo
Abstract:Robotic manipulation policies have made rapid progress in recent years, yet most existing approaches give limited consideration to memory capabilities. Consequently, they struggle to solve tasks that require reasoning over historical observations and maintaining task-relevant information over time, which are common requirements in real-world manipulation scenarios. Although several memory-aware policies have been proposed, systematic evaluation of memory-dependent manipulation remains underexplored, and the relationship between architectural design choices and memory performance is still not well understood. To address this gap, we introduce RMBench, a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity, enabling systematic evaluation of policy memory capabilities. We further propose Mem-0, a modular manipulation policy with explicit memory components designed to support controlled ablation studies. Through extensive simulation and real-world experiments, we identify memory-related limitations in existing policies and provide empirical insights into how architectural design choices influence memory performance. The website is available at this https URL.
| Comments: | website: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.01229 [cs.RO] |
| (or arXiv:2603.01229v4 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2603.01229 arXiv-issued DOI via DataCite |
Submission history
From: Yue Chen [view email]
[v1]
Sun, 1 Mar 2026 18:59:59 UTC (3,032 KB)
[v2]
Sun, 15 Mar 2026 16:53:14 UTC (3,032 KB)
[v3]
Thu, 30 Jul 2026 17:55:22 UTC (3,570 KB)
[v4]
Thu, 15 Oct 2026 17:19:41 UTC (3,994 KB)
来源：arXiv cs.AI · arxiv.org